MCP server for external memory layer for AI agents + more . Download from pypi , and get started

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

Universal memory runtime for AI agents

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

A proposed convention for the .agents/ directory to prevent context bloat and improve agent reasoning in complex codebases.

Poirot is a deep research agent kernel built for those who care about how agents are architected.

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

Your First LLM-Wiki Conversation Knowledge Base

Shared Memory Storage for Multi-Agent Systems

A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.

A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

Artifact layer for agent-human representations. One API call, one SVG. Zero dependencies, renders in any markdown.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec + optional cap hook.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.